TF 2.0 is out! Get hands-on practice at TF World, Oct 28-31. Use code TF20 for 20% off select passes. Register now

tf.contrib.sparsemax.sparsemax

View source on GitHub

Computes sparsemax activations 1.

tf.contrib.sparsemax.sparsemax(
    logits,
    name=None
)

For each batch i and class j we have

\(sparsemax[i, j] = max(logits[i, j] - tau(logits[i, :]), 0)\)

Args:

  • logits: A Tensor. Must be one of the following types: half, float32, float64.
  • name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as logits.